By felvieira
Run a complete autonomous development pipeline — from discovery and spec to parallel implementation, review, security audit, canary deploy, and post-deploy monitoring — using 50 specialist skills and 43 slash commands that enforce quality gates, memory persistence, and context-aware orchestration across backend, frontend, QA, and security disciplines.
Cross-artifact consistency check (read-only) entre constituição, spec, plan e issues — detecta inconsistências, duplicações, ambiguidades e requisitos órfãos antes de /build
Responde pergunta side sem contaminar task atual nem atualizar memória/tasks (adaptado de affaan-m/ECC)
Audita o repositório consumidor — gera docs/repo-audit/current.md + assets.md com stack, convenções, assets, testes, deploy e riscos
Agente autônomo — executa task completa sem intervenção humana até estar pronto, funcional e testado
Auditoria de boas práticas, arquitetura, clean code e DRY (skills 11 + 06 + 05)
Reviewer especializado em detectar e marcar os 29 padrões de AI-generated writing em prosa (docs, PRDs, copy, changelogs, comentários em código). Use quando texto novo entra no repo via PR ou quando swarm/auto produz documentação. Despachar via Task tool para review isolado.
Senior code reviewer focused on clean code, DRY, SOLID, correctness, performance and security. Use when reviewing a PR, a completed feature, or any code that needs validation before merge. Dispatch with Task tool for isolated reviews.
Orquestra build de database CodeQL + execucao de queries de seguranca com taint tracking interprocedural. Use quando Semgrep nao for suficiente (bug envolvendo data flow entre arquivos/funcoes), variant analysis sofisticada, ou auditoria mensal/release major. Mais lento que Semgrep (~5-30min) mas precisao maior. Despache durante a fase 2+ da skill 34.
Systematic debugger that diagnoses root causes, not symptoms. Use when facing a bug, unexpected behavior, failing test, or error you cannot immediately explain. Follows a hypothesis-driven loop with explicit evidence ledger and anti-rationalization tables. Can read, grep, edit and run tests.
Detetive de decisões arquiteturais retroativas em sistemas legados. Identifica escolhas estruturais implícitas (framework, auth, persistência, cache, comunicação) e gera ADRs explicando o que existe e suas consequências — sem julgar nem reescrever. Despache via Task tool durante a Fase 5 do `/detective-spec`. Output em `_detective_sdd/04-adrs/ADR-NNN.md` + síntese em `00-overview.md` e `99-traceability.md`.
Skill de gerenciamento de contexto e tarefas usando o mecanismo de task, memoria ou checklist disponivel no ambiente, com persistencia enxuta entre sessoes quando fizer sentido. Use quando precisar organizar tarefas, acompanhar progresso, trocar foco de trabalho, ou manter historico resumido. Trigger em: "criar tarefa", "lista de tarefas", "status", "progresso", "trocar foco", "resetar contexto", "o que falta", "proxima tarefa", "historico", "pipeline de tarefas".
Skill do Tech Lead/Orquestrador do pipeline de desenvolvimento. Deve ser usada no inicio de toda task e entre etapas relevantes do pipeline. Coordena qual skill executar, em que ordem, adapta o fluxo ao contexto, garante que nenhuma etapa critica seja pulada e mantem visao geral do progresso. Trigger em: "nova task", "iniciar", "pipeline de desenvolvimento", "orquestrar", "coordenar", "planejar execucao", "proximo step do pipeline", "workflow".
Skill de Documentação por nível de decisão. Use quando precisar documentar features, APIs, arquitetura, setup, operação, ou manter documentação existente atualizada. Trigger em: "documentar", "documentação", "docs", "ADR", "architecture decision record", "README", "feature doc", "api doc", "setup doc", "runbook", "troubleshooting", "doc de operação", "registrar decisão", "atualizar docs".
Skill do Reviewer Final para validação completa antes do deploy. Use quando precisar validar que todos os passos do pipeline foram executados, checar qualidade de código, confirmar segurança, confirmar QA, confirmar documentação, ou gerar relatório de aprovação/rejeição. Trigger em: "review final", "reviewer", "aprovação", "rejeição", "validação final", "gate de deploy", "checklist final", "aprovar deploy", "pode deployar", "pronto pra produção", "validar entrega", "review completo", "última verificação".
Skill de Motion Design para animações, transições e micro-interações. Use quando precisar definir ou implementar animações de interface, transições entre páginas, efeitos de hover/click/focus, loading states animados, ou qualquer interação visual com movimento. Trigger em: "animacao", "transicao", "motion", "micro-interacao", "framer motion", "spring", "easing", "parallax", "scroll animation", "hover effect".
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
🇧🇷 Versão em Português · 🌎 English version
A complete team of software specialists inside your coding agent.
Every task is routed to the right specialist, run on the right model, and shipped at production quality.
| Version | Highlight | Where |
|---|---|---|
| v2.37.0 | 7-ebook absorption (Casa do Código) — only the real gap became a new skill: skill 51 ux-research (qualitative discovery — user interview, research-based persona, journey map, usability testing, information architecture; sits before PO 01 and UI/UX 02). The rest became surgical increments: 3 XP policies (pair-programming, continuous-integration, sustainable-pace, wired to skill 37); skill 01 gains a Business Foundation section (hypothesis validation, MVP, monetization, AARRR, product-market fit — from Guia da Startup); skill 14 gains Keyword Research (KEI, intent, long-tail) + Off-Page/Link Building; skill 07 gains Infrastructure as Code (declarative provisioning, idempotency, drift — DevOps principles mapped to Terraform/Ansible); skill 38 gains cohesion/coupling, distributed-seam (REST/async/RPC, HATEOAS) and layer lenses. HTML5 Canvas game-dev dropped (niche <2%). | skills/51-ux-research/SKILL.md, policies/pair-programming.md |
| v2.36.0 | Skill 50 direct-response-copy — direct response copywriting distilled from 3 classic PT-BR copy ebooks: headline formula library in 20 trigger categories (357 models distilled into parameterized formulas), the 8 mental triggers + sales storytelling structure, Instagram caption/engagement copy. Hard integrity gate: no unverifiable claims, no fabricated testimonials, real scarcity only. Complements skill 13 (product copy) — 13 covers landing/microcopy/brand voice, 50 covers ads/sales pages/email/social. | skills/50-direct-response-copy/SKILL.md, skills/50-direct-response-copy/references/headline-formulas.md |
| v2.29.0 | Claim verifier + context hygiene — two PostToolUse/UserPromptSubmit hooks: (1) claim-verifier detects output with unverified result claims ("email sent", "deploy OK", "tests passed", "migration ran") and injects the specific command to verify before asserting — passes free if inline evidence present (exit code 0, HTTP 200, query result); (2) context-turn-counter suggests /compact every 25 turns and recommends full session handoff at 50 turns (save to D:\claude-memory\logs\, open new session with resumption prompt). New policy: claim-verification.md. Two new GLOBAL.md defaults: "verify before asserting" + "compact proactively". | hooks/scripts/claim-verifier.mjs, hooks/scripts/context-turn-counter.mjs, policies/claim-verification.md |
| v2.28.0 | SDD absorption from Medium articles — 3 additions inspired by "Spec-Driven Development with AI Coding Agents" + "Claude Code plugins" articles: (1) /spec-kit unified SDD pipeline (specify→plan→tasks→implement with explicit checkpoints + inline Adversarial Verifier); (2) /swarm upgraded with Phase 3 Adversarial Verify (Implementor vs Verifier with opposing goals — verifier tries to refute, spec updated in real-time from gaps found); (3) /insights usage-based recommendations (reads hook telemetry JSONLs — gate decisions, investigate-first blocks, tool repetitions — recommends what to calibrate). | commands/spec-kit.md, commands/insights.md, commands/swarm.md |
| v2.27.0 | Investigate-first guard — a principle with active enforcement: the AI must never ask the user something it can discover itself. New PreToolUse hook intercepts AskUserQuestion, detects self-discoverable questions (github user, gh logged-in, branch, package manager, port, runtime version, stack, MCP account) and tells the model to run the command first (gh auth status, git config, Glob lockfile, MCP whoami) instead of interrupting. Doesn't block — educates. Conservative: preference/intent/trade-off questions pass through. 10/10 discoverable patterns caught, 5/5 legit questions pass. | policies/investigate-first.md, hooks/scripts/investigate-first-guard.mjs |
npx claudepluginhub felvieira/claude-skills-fv --plugin dev-team-kit-fvGive soul to your workflow. 58 AI-powered skills across 17 roles — PM, Dev, Backend, Frontend, QA, UX, Data, Detect, WordPress, Release, Security, DevOps, and Core. Spec-to-ship pipeline: scaffold, implement, test, secure, deploy. Features two-phase workflow with human approval, quality-reviewer agent, token optimization, and continuous improvement via LEARN.md system.
12 PM-specific agent skills, 6 workflow commands, 3 automation hooks for Product Managers
🚀 Quick Flow Solo Dev — Elite Full-Stack Developer + Quick Flow Specialist
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Lean agent skills for building, shipping, strategy, and growth — no context bloat.